1. The utility model provides a big data diagnostic system in high in clouds based on artificial intelligence which characterized in that: the system comprises a cloud database module, a personal vital sign data flow module and an AI deep learning and diagnosis module;

the personal vital sign data flow module acquires data of vital signs of a user or an individual and transmits the data to the cloud database module, the AI deep learning module collects a large amount of medical record data and learns, the AI deep learning module transmits the processed data to the cloud database module, the cloud database module stores the data of the personal vital sign data flow module and the AI deep learning module and transmits the data to the diagnosis module, and the diagnosis module can remotely judge the state of the body of the patient or the individual according to the vital sign data flow of the user and predict diseases.

2. The cloud big data diagnosis system based on artificial intelligence of claim 1, wherein: the personal vital sign data flow module comprises one or more of an electronic blood pressure meter, a pulse phase sensor and a digital electrocardiogram meter, wherein the electronic blood pressure meter is used for measuring a pulse phase waveform diagram of a user in a blood pressure state or under different wrist pressure conditions; the pulse phase sensor is used for detecting pulse signal oscillograms of the user in different pressure intensity states; the electrocardiograph is used for measuring the electrocardiogram of a user and acquiring an electrocardiogram waveform graph.

3. The cloud big data diagnosis system based on artificial intelligence of claim 2, wherein: the human vital sign data flow module further comprises a vital sign sensor for monitoring the blood oxygen protection degree, the body temperature, the pulse rate, the non-invasive blood pressure and the mean arterial pressure of a user in real time, a pulse phase oscillogram under different wrist pressure conditions and one or more types of electrocardiograms.

4. The cloud big data diagnosis system based on artificial intelligence of claim 1, wherein: the AI deep learning module matches data generated by the human vital sign data flow module of the user with medical records.

5. The artificial intelligence based cloud big data diagnosis system according to claim 4, wherein: the AI deep learning module comprises a personal medical record data stream, which collects, stores and classifies medical records of patients.

6. The cloud big data diagnosis system based on artificial intelligence of claim 1, wherein: the diagnostic module includes a monitoring module for monitoring health data of a patient or person in real time.

7. The cloud big data diagnosis system based on artificial intelligence of claim 6, wherein: the diagnostic module also includes a low cost medical health system for assisting in diagnosis.

Background

The medical diagnosis process is a chain formed by diagnosing people, diseases, types and syndromes, and differentiating people, diseases, types and syndromes, so as to form a unified whole. This requires that the physician comprehensively grasp the disease, reveal the nature of the disease as much as possible, and study all of its links and "mediators"; secondly, revealing the development and movement of diseases, analyzing the essence of the diseases by using historical attitudes, and grasping the transformation and transition rule from one person, disease, type and syndrome to another person, disease, type and syndrome; thirdly, the contradictory nature of the disease must be revealed, since only the contradictory nature of the disease is mastered, a true diagnosis is obtained; fourthly, the diagnosis must newly include prevention and treatment plans and medical practices, which are also the judgment standard for the correctness of the diagnosis, and all the bases of the diagnosis are clinical practices; the big data is used as the expression of the mature development of the internet, more and more data resources and operation guarantee are provided, the development of the internet enables people to obtain knowledge in many aspects on the internet, the knowledge comprises medical treatment and disease condition information, the information is compared with the information per se to recognize the severity of certain disease condition, in addition, opaque medical treatment modes and medication modes lead doctors and patients to have a one-step shortage, the frequent occurrence of injury time is caused, a medical system needs a complete management system, medicines and expenses can be strictly monitored, controlled and controlled, patients can know the severity of the disease condition in advance, when receiving the treatment of medical resources, the medical personnel cannot be injured due to the ignorance of the disease condition, and the fact that the medical accident event is relieved of responsibility and evaded by medical workers is avoided.

At present, the collection and the update of the hospitalization information of the hospital are generally adopted, so that the patient can make an appointment on the internet, and a powerful hospital and a doctor are selected for consultation, but the operations are only convenient, the queuing time is avoided, the purpose of intelligent medical treatment is not achieved, and the cost of medical diagnosis is increased.

Disclosure of Invention

Technical problem to be solved

Aiming at the defects of the prior art, the invention provides a cloud big data diagnosis system based on artificial intelligence, which has the advantages of diagnosing patients based on big data and AI learning and partially solves the problems of complex medical diagnosis and high cost.

(II) technical scheme

In order to achieve the purpose, the invention provides the following technical scheme: a cloud big data diagnosis system based on artificial intelligence comprises a cloud database module, a personal vital sign data flow module, an AI deep learning module and a diagnosis module;

the personal vital sign data flow module acquires data of vital signs of patients or individuals and transmits the data to the cloud database module, the AI deep learning module collects a large amount of medical record data and learns, the AI deep learning module transmits the processed data to the cloud database module, the cloud database module stores the data of the personal vital sign data flow module and the AI deep learning module and transmits the data to the diagnosis module, and the diagnosis module can remotely judge the body state of the patients or individuals and predict diseases according to the vital sign data flow of the users.

Preferably, the personal vital sign data flow module includes one or more of an electronic blood pressure meter, a pulse phase sensor and a digital electrocardiogram meter, the electronic blood pressure meter is used for measuring a blood pressure state of the user or a pulse phase waveform diagram (refer to pulse feeling of traditional Chinese medicine) under different wrist pressure conditions, the pulse phase sensor is used for detecting the pulse phase waveform diagram under different wrist pressure conditions of the user, and the electrocardiogram meter is used for measuring an electrocardiogram of the user and acquiring the electrocardiogram waveform diagram, so as to provide basic data for learning and matching for the AI.

By adopting the scheme: the electronic blood pressure monitor adopts an oscillography method, and is accurate in principle. Clinical validation of electronic sphygmomanometers is designed using statistical methods with the auscultatory method as a standard. However, this does not mean that the results obtained by the auscultatory method using the mercury pressure gauge are more accurate than those obtained by the electronic sphygmomanometer. Of course, it is not necessarily true that the measurement result of the electronic blood pressure monitor is more accurate than the result measured by the auscultation method using the mercury pressure gauge; the pulse refers to the pulse of the artery, and the pulse sensor is used for detecting the pressure change generated during the pulse of the artery and converting the pressure change into an electric signal which can be more intuitively observed and detected. The pulse sensor has two output modes of analog output and digital output. The method can be mainly divided into a piezoelectric type, a piezoresistive type, a photoelectric type and the like according to the signal acquisition mode. The piezoelectric type and the piezoresistive type convert the pressure process of pulse pulsation into signals and output the signals through micro-pressure type materials (piezoelectric sheets, bridges and the like). The photoelectric pulse sensor converts the change of the light transmittance of the blood vessel in the pulse beating process into a signal to be output in a reflection or correlation mode.

Preferably, the human vital sign data flow module further comprises a vital sign sensor for monitoring one or more of blood oxygen protection, body temperature, pulse rate, non-invasive blood pressure, mean arterial pressure of the user, pulse phase oscillograms under different wrist pressure conditions, and electrocardiogram in real time.

Preferably, the AI deep learning module matches the data generated by the human vital sign data flow module of the user with medical records.

The data generated by the human vital sign data flow module comprises data generated by vital sign sensors such as pulse phase graphs, blood oxygen protection degrees, body temperature, pulse rate, noninvasive blood pressure, mean arterial pressure, electrocardiogram and the like or data obtained after processing.

By adopting the scheme: artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence, a field of research that includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. Since the birth of artificial intelligence, theories and technologies become mature day by day, and application fields are expanded continuously, so that science and technology products brought by the artificial intelligence in the future can be assumed to be 'containers' of human intelligence. The artificial intelligence can simulate the information process of human consciousness and thinking. The artificial intelligence is not human intelligence, but can think like a human, or can exceed the human intelligence, and multiple medical records are compared by the artificial intelligence.

Preferably, the AI deep learning module includes a personal medical record data stream, which collects, stores and classifies medical records of a plurality of patients, learns and matches the vital sign data stream and the user medical record data stream, and can be invoked at any time.

Preferably, the diagnostic module comprises a monitoring module for monitoring health data of the patient or person in real time.

Preferably, the diagnostic module further comprises a low-cost medical health system for assisting a user or a doctor in diagnosis and treatment.

(III) advantageous effects

Compared with the prior art, the invention provides a cloud big data diagnosis system based on artificial intelligence, which has the following beneficial effects:

this big data diagnostic system in high in clouds based on artificial intelligence, but collect individual vital sign condition and real-time observation through individual vital sign dataflow, and collect a large amount of medical history data by AI deep learning module, compare and match individual vital sign data and individual medical history data by AI deep learning module, compare pulse phase figure and case history, data transmission after will matching is to the high in clouds database in, the data after will matching is stored and is handled by the high in clouds database module, and can be with data transfer to the diagnostic module in, judge the disease that individual exists or the prediction that has the disease by the diagnostic module, thereby the cost of individual medical diagnosis has been reduced, thereby supplementary user or doctor's diagnosis and treatment. The human physical resources required by medical diagnosis can be greatly saved, and a data foundation is laid for the establishment of a low-cost medical system.

Drawings

FIG. 1 is a schematic diagram of the system architecture of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example one

A cloud big data diagnosis system based on artificial intelligence comprises a cloud database module, a personal vital sign data flow module, an AI deep learning module and a diagnosis module;

the personal vital sign data flow module acquires data of vital signs of patients or individuals and transmits the data to the cloud database module, the AI deep learning module collects a large amount of medical record data and learns, the AI deep learning module transmits the processed data to the cloud database module, the cloud database module stores the data of the personal vital sign data flow module and the AI deep learning module and transmits the data to the diagnosis module, and the diagnosis module can judge the body state of the patients or individuals and predict diseases.

Referring to fig. 1: the personal vital sign data flow equipment is used for collecting and observing personal vital sign conditions in real time, the AI deep learning module is used for collecting, arranging and matching a large amount of personal medical record data, the AI deep learning module is used for matching and comparing the personal vital sign data with the personal medical record data, a pulse phase graph and a medical record are compared, the internal mathematical law between the human vital sign data flow and the medical record is mastered through big data matching, the pulse phase graph comparison and the medical record comparison are compared in a separated mode, the matched data are transmitted to the cloud database, the cloud database module is used for storing and processing the matched data, the data can be transmitted into the diagnosis module, the diagnosis module is used for judging personal diseases or predicting the diseases, and the cost of personal medical diagnosis is greatly reduced, thereby accurately obtaining the existing diseases of the individual.

Specifically, the personal vital sign data flow module includes an electronic blood pressure monitor for measuring a blood pressure state of the patient or the person, and a pulse phase sensor for detecting a pulse signal of the patient or the person.

The electronic blood pressure monitor adopts an oscillography method, and is accurate in principle. Clinical validation of electronic sphygmomanometers is designed using statistical methods with the auscultatory method as a standard. However, this does not mean that the results obtained by the auscultatory method using the mercury pressure gauge are more accurate than those obtained by the electronic sphygmomanometer. Of course, it is not necessarily true that the measurement result of the electronic blood pressure monitor is more accurate than the result measured by the auscultation method using the mercury pressure gauge; the pulse refers to the pulse of the artery, and the pulse sensor is used for detecting the pressure change generated during the pulse of the artery and converting the pressure change into an electric signal which can be more intuitively observed and detected. The pulse sensor has two output modes of analog output and digital output. The method can be mainly divided into a piezoelectric type, a piezoresistive type, a photoelectric type and the like according to the signal acquisition mode. The piezoelectric type and the piezoresistive type convert the pressure process of pulse pulsation into signals and output the signals through micro-pressure type materials (piezoelectric sheets, bridges and the like). The photoelectric pulse sensor converts the change of the light transmittance of the blood vessel in the pulse beating process into a signal to be output in a reflection or correlation mode.

Specifically, the human vital sign data flow module further comprises a vital sign sensor for monitoring blood oxygen protection level, body temperature, pulse rate, non-invasive blood pressure, mean arterial pressure, dynamic pulse phase, electrocardiogram and the like of the patient or the individual in real time.

Specifically, the AI deep learning module matches the pulse phase pattern with the medical record.

Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence, a field of research that includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others. Since the birth of artificial intelligence, theories and technologies become mature day by day, and application fields are expanded continuously, so that science and technology products brought by the artificial intelligence in the future can be assumed to be 'containers' of human intelligence. The artificial intelligence can simulate the information process of human consciousness and thinking. The artificial intelligence is not human intelligence, but can think like a human, or can exceed the human intelligence, and multiple medical records are compared by the artificial intelligence.

Specifically, the AI deep learning module includes a personal medical record data stream that collects, stores, and classifies medical records of a plurality of patients;

the medical record data flow is mainly divided into a pulse picture and a medical record of a user, the two kinds of data of the user are separated, and model design is respectively set; the method comprises the steps of inputting a given pulse picture, setting and operating the picture through model design to obtain a characteristic value or a characteristic function of the pulse picture, generating a picture discriminant according to each characteristic or characteristic function of the picture, and selecting a corresponding picture discriminant from a picture discriminant set.

Specifically, the diagnostic module includes a monitoring module for monitoring health data of a patient or person in real time.

In particular, the diagnostic module further comprises a low cost medical health system for assisting a user in performing a treatment.

The diagnosis module compares the pulse picture and the medical record of the individual with the data in the database module, the AI deep learning module compares the characteristic value with the input characteristic value to predict the disease possibly suffered by the individual, the medical health system comprises a portable terminal device, an intelligent doctor platform and a remote center, the terminal device gives out corresponding indication and transmits the indication to the intelligent doctor platform, the remote center transmits the comparison condition between the individual and the database to the doctor platform, the doctor platform gives out a corresponding solution mode, the portable terminal device can monitor the electrocardio condition of the individual and transmit the electrocardio condition to the remote center, and real-time comparison can be achieved, and the disease condition of the patient can be predicted.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.